chaiml-elite-feed-convo-_1137

submission_id: chaiml-elite-feed-convo-_1137_v1

developer_uid: zonemercy

alignment_samples: 10616

alignment_score: 0.02735654200110977

best_of: 8

celo_rating: 1250.15

display_name: chaiml-elite-feed-convo-_1137_v1

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '{user_name}: {message}</s>', 'response_template': '{bot_name}:', 'truncate_by_message': True}

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: True

language_model: ChaiML/Elite-Feed-Convo-v1-1e5ep2

latencies: [{'batch_size': 1, 'throughput': 0.6176239087439848, 'latency_mean': 1.619021921157837, 'latency_p50': 1.6190965175628662, 'latency_p90': 1.7805872678756713}, {'batch_size': 3, 'throughput': 1.0835773512470994, 'latency_mean': 2.760998160839081, 'latency_p50': 2.755523443222046, 'latency_p90': 3.0493351936340334}, {'batch_size': 5, 'throughput': 1.2371354264620502, 'latency_mean': 4.022749562263488, 'latency_p50': 4.020741581916809, 'latency_p90': 4.466355895996093}, {'batch_size': 6, 'throughput': 1.2748920997484925, 'latency_mean': 4.680998382568359, 'latency_p50': 4.690432786941528, 'latency_p90': 5.318770384788513}, {'batch_size': 8, 'throughput': 1.2445489280726891, 'latency_mean': 6.397218989133835, 'latency_p50': 6.4078991413116455, 'latency_p90': 7.340734744071961}, {'batch_size': 10, 'throughput': 1.2125051749245404, 'latency_mean': 8.188314464092254, 'latency_p50': 8.250919580459595, 'latency_p90': 9.317851996421814}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/Elite-Feed-Convo-

model_name: chaiml-elite-feed-convo-_1137_v1

model_num_parameters: 12772070400.0

model_repo: ChaiML/Elite-Feed-Convo-v1-1e5ep2

model_size: 13B

num_battles: 10616

num_wins: 5432

propriety_score: 0.7213290460878885

propriety_total_count: 933.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.21

timestamp: 2024-09-11T21:15:51+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.5116804822908817

Download Preference Data

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-elite-feed-convo-1137-v1-mkmlizer
Waiting for job on chaiml-elite-feed-convo-1137-v1-mkmlizer to finish
chaiml-elite-feed-convo-1137-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║       /___/                                                         ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ║                                                                     ║
chaiml-elite-feed-convo-1137-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elite-feed-convo-1137-v1-mkmlizer: Downloaded to shared memory in 102.390s
chaiml-elite-feed-convo-1137-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0kaq9x3x, device:0
chaiml-elite-feed-convo-1137-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elite-feed-convo-1137-v1-mkmlizer: quantized model in 41.267s
chaiml-elite-feed-convo-1137-v1-mkmlizer: Processed model ChaiML/Elite-Feed-Convo-v1-1e5ep2 in 143.657s
chaiml-elite-feed-convo-1137-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elite-feed-convo-1137-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elite-feed-convo-1137-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elite-feed-convo-1137-v1
chaiml-elite-feed-convo-1137-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1137-v1/config.json
chaiml-elite-feed-convo-1137-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1137-v1/special_tokens_map.json
chaiml-elite-feed-convo-1137-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1137-v1/tokenizer_config.json
chaiml-elite-feed-convo-1137-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elite-feed-convo-1137-v1/tokenizer.json
chaiml-elite-feed-convo-1137-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elite-feed-convo-1137-v1/flywheel_model.0.safetensors
chaiml-elite-feed-convo-1137-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.15it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 29.01it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.71it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.93it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 25.50it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 24.86it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 23.71it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.13it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.68it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.34it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.89it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.29it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.38it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.42it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 26.48it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 26.47it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:11, 24.31it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 29.01it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.99it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.13it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.69it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.91it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 21.85it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.65it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.87it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.16it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.63it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.19it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.31it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.06it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.69it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.21it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.19it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 29.43it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.16it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 29.95it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.86it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.94it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 25.45it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.62it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.99it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 26.94it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 24.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.94it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.72it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.55it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.12it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.77it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 26.04it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.64it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.45it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 28.47it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 25.10it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.41it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.06it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.39it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.13it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.10it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 27.36it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 25.22it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 32.03it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.74it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.65it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.20it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.43it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 26.60it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.85it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.41it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.04it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.77it/s]
Loading 0:  90%|████████▉ | 325/363 [00:11<00:01, 28.81it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.84it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 32.28it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.09it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.04it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.90it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.03it/s]
                                                            
Job chaiml-elite-feed-convo-1137-v1-mkmlizer completed after 167.46s with status: succeeded
Stopping job with name chaiml-elite-feed-convo-1137-v1-mkmlizer
Pipeline stage MKMLizer completed in 169.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elite-feed-convo-1137-v1
Waiting for inference service chaiml-elite-feed-convo-1137-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-elite-feed-convo-1137-v1 ready after 171.23656821250916s
Pipeline stage MKMLDeployer completed in 173.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4651246070861816s
Received healthy response to inference request in 2.3340866565704346s
Received healthy response to inference request in 2.2265186309814453s
Received healthy response to inference request in 2.3028581142425537s
Received healthy response to inference request in 1.6657023429870605s
5 requests
0 failed requests
5th percentile: 1.7778656005859375
10th percentile: 1.8900288581848144
20th percentile: 2.114355373382568
30th percentile: 2.241786527633667
40th percentile: 2.2723223209381103
50th percentile: 2.3028581142425537
60th percentile: 2.3153495311737062
70th percentile: 2.3278409481048583
80th percentile: 2.560294246673584
90th percentile: 3.012709426879883
95th percentile: 3.238917016983032
99th percentile: 3.419883089065552
mean time: 2.398858070373535
Pipeline stage StressChecker completed in 13.08s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.37s
Shutdown handler de-registered
chaiml-elite-feed-convo-_1137_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elite-feed-convo-1137-v1-profiler
Waiting for inference service chaiml-elite-feed-convo-1137-v1-profiler to be ready
Inference service chaiml-elite-feed-convo-1137-v1-profiler ready after 170.40870547294617s
Pipeline stage MKMLProfilerDeployer completed in 170.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elite-feed-co544f197275200d7d4b1e124050177f72-deplo87kbf:/code/chaiverse_profiler_1726089925 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elite-feed-co544f197275200d7d4b1e124050177f72-deplo87kbf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726089925 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726089925/summary.json'
kubectl exec -it chaiml-elite-feed-co544f197275200d7d4b1e124050177f72-deplo87kbf --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726089925/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1160.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elite-feed-convo-1137-v1-profiler is running
Tearing down inference service chaiml-elite-feed-convo-1137-v1-profiler
Service chaiml-elite-feed-convo-1137-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.84s
Shutdown handler de-registered
chaiml-elite-feed-convo-_1137_v1 status is now inactive due to auto deactivation removed underperforming models